QECLO: A Novel QoS-Aware Joint Optimization of Energy and Latency for VFC Task Offloading
Chenyi Liang, Zhibin Gao, Bo Wang, Keyi Cheng, Yifeng Zhao · 2024
Artificial Intelligence Internet of Things (AIoT) is an emerging technology within the Internet of Things (IoT), bringing an increasing demand for intelligent task offloading. Multi-node cooperative Vehicular Fog Computing (VFC) offers efficient and low-latency data processing to meet this requirement. However, due to the limited resource of fog nodes and latency-sensitive and computing-intensive task requirements, how to efficiently improve Quality of Service (QoS) and reduce energy consumption is an important issue in VFC. In this paper, we propose QECLO, a novel QoS-aware task offloading method. Unlike most previous studies, our goal is to improve QoS while minimizing energy consumption thus avoiding the overallocation of resource and high energy consumption caused by the one-sided pursuit of high QoS for few high-priority tasks. We solve the computation resource allocation subproblem by convex optimization and then optimize the communication resource and power allocation by an improved heuristic algorithm based on Decision Tree (DT). Moreover, we evaluate proposed approach through traffic scenario simulations. The experimental results show that our proposed approach outperforms existing methods in terms of energy consumption and latency.